[KongchangAI]
Model

Qwen3-4B-Base

A base language model in Alibaba's Qwen series with 4B parameters, suitable for research and fine-tuning.

Timeline (last 90 days)

Nov 11

Reproduction experiments on Qwen3-4B-Base show that MCPO also improves over GRPO, with all three seeds positive and an average improvement of 4.75 points.

Unverified50%
Oct 15

In the RLVR experiments on Qwen3-4B-Base, with both the SGD+EMA and AdamW optimizers, configurations choosing a larger momentum coefficient showed an advantage.

Unverified50%
Oct 7

Fiorillo v0.5 uses Qwen3-4B-Base as its backbone, with a low-rank adapter (LoRA) and a dedicated decision head stacked on top, fine-tuned exclusively for the EI task.

Unverified50%

All Facts (3)

Source Articles